Claude-assisted protein designs reportedly yield 17 scorpion toxin binders

Two designs targeting the Cn2 toxin, Cn2-B1 and Cn2-B2, bound it with single-digit nanomolar affinities at both labs, according to Anthropic. Its competition experiments suggest they attach on or near the site of a previously reported toxin-neutralizing antibody. That is a lead for further testing, not a demonstration that either design neutralizes the toxin.

The reported tests measured binding to lab-made recombinant toxins, not toxins purified from venom. Anthropic says it did not test any design for toxin neutralization in lab-grown cells or for effectiveness in living animals, so it does not claim to have produced an antivenom. The company says it is releasing all 211 designs and their binding data for other researchers.

Many accounts welcomed Claude’s protein design work for enabling real lab-tested scientific discovery, while others dismissed the claims as prompt chaining that wastes compute and restricts access.

Based on 64 sentiment-bearing replies from 59 accounts across 2 conversations.

Many accounts welcomed Claude’s protein design work for enabling real lab-tested scientific discovery, while others dismissed the claims as prompt chaining that wastes compute and restricts access.

Based on 64 sentiment-bearing replies from 59 accounts across 2 conversations.